Selecting the Best Multinomial Cell-Provided it is Better than a Control

✍ Scribed by Prof. P. Chen

• Publisher: John Wiley and Sons
• Year: 1988
• Tongue: English
• Weight: 375 KB
• Volume: 30
• Category: Article
• ISSN: 0323-3847
• DOI: 10.1002/bimj.4710300815

✦ Synopsis

BECEHOFER and TURNBULL (1978) considered the problems of selecting the best normal popUl8tion, provided it is better than a standard for the case of known variances or equal but unknown variances. Wmcox (1984) considered the same selection goal for the case of unequal unknown variance and provided the appropriate probability equations and the neceasary table. Under the same selection formulation (which we will describe formally in the following sections), this article studies a class of composite inverse sampling procedures for selecting the best multinomial cell that is better than a control cell with unknowncell probability. The procedures guaraiitee that (a) with probability a t least Pg (specified), no cell is selected when the largest cell probability is sufficiently less than the control and (b), with probability a t least P f (specified), the cell with the largest probability is selected when its probability is sufficiently greater than the second largext cell probability and the control cell probability.